Triple
T37458303
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aggro Shaman |
E930853
|
entity |
| Predicate | damageDistribution |
P189388
|
FINISHED |
| Object | High proportion of damage directed at opponent hero |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: High proportion of damage directed at opponent hero | Statement: [Aggro Shaman, damageDistribution, High proportion of damage directed at opponent hero]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: damageDistribution Context triple: [Aggro Shaman, damageDistribution, High proportion of damage directed at opponent hero]
-
A.
damageRating
Indicates the assessed level or severity of damage associated with an entity or event.
-
B.
damageBasis
Indicates the underlying reason, cause, or basis on which damage is determined or assessed in a given context.
-
C.
damageEffect
Indicates that one entity causes harm, reduction, or deterioration to another entity or its properties.
-
D.
damageLeadsTo
Indicates that one instance of damage causally results in or contributes to another specified outcome or condition.
-
E.
damageScope
Indicates the extent or range of harm or impairment caused by an event, action, or condition.
- F. None of above. chosen
Provenance (4 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f76ec1a1148190b0a961f188d621b0 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbbc49da8c8190902bbb05d2477cab |
completed | May 6, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69fbb13f34b08190bbbb220ac1e6e666 |
completed | May 6, 2026, 9:23 p.m. |
| PDg | Predicate description generation | batch_69fbbc48b75c8190bec27dd4b7de797f |
completed | May 6, 2026, 10:10 p.m. |
Created at: May 3, 2026, 4:17 p.m.